Classification of speech under stress based on features derived from the nonlinear Teager energy operator

Studies have shown that distortion introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help neutralize stressed speech and improve robust-ness of speech recognition systems. Although some acoustic variables derived from linear speech production theory have been investigated as indicators of stress, they are not consistent. In this paper, three new features derived from the nonlinear Teager Energy Operator (TEO) are investigated for stress assessment and classiication. It is believed that TEO based features are better able to reeect the nonlinear airrow structure of speech production under adverse stressful conditions. The proposed features outperform stress classiication using traditional pitch by +22:5% for the Normalized TEO Autocorrelation Envelope Area feature (TEO-Auto-Env), and by +28:8% for TEO based Pitch feature (TEO-Pitch). Overall neutral/stress classiication rates are more consistent for TEO based features (TEO-Auto-Env: = 5:15, TEO-Pitch: = 7:83) vs. (Pitch: = 23:40). Also, evaluation results using actual emergency aircraft cockpit stressed speech from NATO show that TEO-Auto-Env works best for stress assessment.